Biography

Francesco Branda is a Ph.D. in Information and Communication Technologies (ICT) at the Department of Computer Science, Modeling, Electronics and Systems Engineering (DIMES) of the University of Calabria, Italy. His current research focuses on big data analysis, social media analysis, high performance computing, and machine learning. In particular, he has published several scientific papers in international conference and journals, in the following research topics:

  • Machine learning and data mining algorithms;
  • Innovative applications of Big Data computing;
  • Data science approaches to infectious disease surveillance and modeling;
  • Methods, techniques, and prototypes designed and used to implement Big Data solutions on massive data sources which requires using high-performance computing systems.

He is also a member of DtoK Lab S.r.l, an academic spin-off of University of Calabria, and the Scalable Computing e Cloud Laboratory.

Education

  • PhD in Information and Communication Technologies, 2023

    University of Calabria

  • M.Sc. in Computer Engineering, 2019

    University of Calabria

  • B.Sc. in Computer Engineering, 2016

    University of Calabria

Publications

(2023). Epidemic history and evolution of an emerging threat of international concern, the severe acute respiratory syndrome coronavirus 2. Journal of Medical Virology.

PDF DOI

(2023). Is a new COVID-19 wave coming from China due to an unknown variant of concern? Keep calm and look at the data. Journal of Medical Virology.

PDF DOI

(2023). Statistical models to predict clinical outcomes with anakinra vs. tocilizumab treatments for severe pneumonia in COVID19 patients. European Journal of Internal Medicine.

DOI

Posts

Distributed Deep Learning Pipelines with PySpark and Keras

Distributed Deep Learning Pipelines with PySpark and Keras

Deep learning has achieved great success in many areas recently. It has attained state-of-the-art performance in applications ranging from image classification and speech recognition to time series forecasting. The key success factors of deep learning are – big volumes of data, flexible models and ever-growing computing power. With the increase in the number of parameters and training data, it is observed that the performance of deep learning can be improved dramatically.

Contributions

The beauty of (open) data will save public global health

How many of us can remember our friends’ phone numbers, how many can keep in mind all the passwords to access each device? It is not just due to a lack of training if we cannot remember everything, but because we live in a highly data-driven world. Every day we are immersed by information in the form of data, we ourselves are turned into information where we browse online to buy something, express our preferences, search for the next vacation destination. The world has changed since it became possible to translate it into bits and transfer it to hardware.
The beauty of (open) data will save public global health

Is climate change causing a resurgence in infectious diseases?

The clock is ticking to restore our relationship with nature to one that is mutually beneficial, not detrimental to our existence
Is climate change causing a resurgence in infectious diseases?

Una mentalità data-driven per rispondere alle pandemie

Il progetto pilota del portale open source di sorveglianza epidemiologica cerca di rispondere alla sfida del rilascio e mantenimento dei dati open, sviluppando una rete sempre più numerosa di esperti. L’obiettivo è condividere e valorizzare i dati in un’ottica One Health, basandosi sulla collaborazione intersettoriale per supportare il rilevamento, il monitoraggio e la valutazione del rischio per le malattie infettive emergenti e riemergenti in Europa.
Una mentalità data-driven per rispondere alle pandemie

Sanremo 2023: le parole e le emozioni secondo Twitter

Da qualche anno a questa parte il social è diventato lo specchio del gradimento degli spettatori appassionati del Festival. Ecco quali sono state le parole più citate e gli artisti più apprezzati sul web nel corso delle prime due serate del Festival.
Sanremo 2023: le parole e le emozioni secondo Twitter

Dojo: newsletter Dataninja

Dojo: newsletter Dataninja

Projects

COVIDA: COrona VIrus Data Analytics

The COVIDA project is dedicated to the collection and visualization of data related to the COVID-19 emergency in Calabria and makes available to the scientific community all the necessary information, such as the total number of infections recorded on the territory, with a series of detailed indications (hospitalized, cured, deceased, number of swabs performed) to monitor and classify the epidemic risk, and the number of subjects vaccinated with the first dose, those vaccinated with a full cycle, the progress of vaccinations by category and age group, to evaluate the progress of the vaccination campaign. The platform can be reached at the link https://covida.ml/
COVIDA: COrona VIrus Data Analytics

ASPIDE: exAScale ProgramIng models for extreme Data procEssing

The ASPIDE project will contribute with the definition of a new programming paradigms, APIs, runtime tools and methodologies for expressing data-intensive tasks on Exascale systems, which can pave the way for the exploitation of massive parallelism over a simplified model of the system architecture, promoting high performance and efficiency, and offering powerful operations and mechanisms for processing extreme data sources at high speed and/or real-time.
ASPIDE: exAScale ProgramIng models for extreme Data procEssing